Exercise short-stack calibration paths

CLAUDE.md

@@ -15,6 +15,7 @@ export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
 ./gradlew :sim:test                    # fast calibration-policy tests
 ./gradlew :sim:run --args="styles"     # enforced controlled style experiment
 ./gradlew :sim:run --args="calibrate"  # enforced 4×100k fixed-pool skill + style calibration
+./gradlew :sim:run --args="short-stacks" # persistent stacks; asserts side-pot/call-clamp coverage
 ./gradlew :app:assembleDebug           # build the APK
 ```
 
@@ -48,6 +49,8 @@ export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
 4. **The simulator is how bots get tuned.** Run it after any bot change, across
    several seeds — a single seed will happily agree with a wrong conclusion.
    The quick 50k run is diagnostic; only `calibrate` is an enforced result.
+   Its paired skill comparisons reset equal stacks to isolate skill, then a
+   mandatory persistent-stack pass verifies that short-stack pricing is live.
 5. **A skill parameter must not smuggle in a style change.** Several bugs came
    from exactly this: `positionAwareness` silently reduced hands played,
    `potOddsRespect` systematically loosened weak players (which is a *winning*
@@ -77,6 +80,10 @@ export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
 - Small samples lie. 1,000 hands is not enough to rank profiles. Use the paired
   4×100k fixed-opponent calibration before accepting a skill change; it computes
   confidence bounds and exits nonzero when the contract fails.
+- Equal starting stacks are deliberate in the paired skill experiment, but they
+  cannot exercise side-pot pricing. `calibrate` therefore finishes with 3,000
+  persistent-stack hands and fails unless both `eligiblePot != pot` and
+  `toCall > stack` occur. `:sim:test` pins the same paths at a fixed seed.
 
 ## Status
 
@@ -95,6 +102,8 @@ export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
   are allowed to overlap, but both must beat Intermediate and Intermediate must
   beat Beginner with a positive 95% lower confidence bound. Current lower bounds
   are +24.42, +11.01, and +24.67 bb/100 respectively.
+- Persistent-stack calibration currently reaches 351 decisions with inaccessible
+  side-pot chips and stack-clamped calls in 3,000 hands (seed 20260729).
 - Expert differs by mechanism: it alone maintains opponent reads. The aggression
   prior is measured by the controlled neutral TAG experiment (0.231 observed,
   0.22 configured), not selected because it looks plausible.